60b1967c39
Add the scratch wave offset to the scratch buffer descriptor (SRSrc) in the entry function prologue. This allows us to removes the scratch wave offset register from the calling convention ABI. As part of this change, allow the use of an inline constant zero for the SOffset of MUBUF instructions accessing the stack in entry functions when a frame pointer is not requested/required. Entry functions with calls still need to set up the calling convention ABI stack pointer register, and reference it in order to address arguments of called functions. The ABI stack pointer register remains unswizzled, but is now wave-relative instead of queue-relative. Non-entry functions also use an inline constant zero SOffset for wave-relative scratch access, but continue to use the stack and frame pointers as before. When the stack or frame pointer is converted to a swizzled offset it is now scaled directly, as the scratch wave offset no longer needs to be subtracted first. Update llvm/docs/AMDGPUUsage.rst to reflect these changes to the calling convention. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75138
81 lines
3.1 KiB
C++
81 lines
3.1 KiB
C++
//===--------------------- SIFrameLowering.h --------------------*- C++ -*-===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_AMDGPU_SIFRAMELOWERING_H
|
|
#define LLVM_LIB_TARGET_AMDGPU_SIFRAMELOWERING_H
|
|
|
|
#include "AMDGPUFrameLowering.h"
|
|
|
|
namespace llvm {
|
|
|
|
class SIInstrInfo;
|
|
class SIMachineFunctionInfo;
|
|
class SIRegisterInfo;
|
|
class GCNSubtarget;
|
|
|
|
class SIFrameLowering final : public AMDGPUFrameLowering {
|
|
public:
|
|
SIFrameLowering(StackDirection D, Align StackAl, int LAO,
|
|
Align TransAl = Align(1))
|
|
: AMDGPUFrameLowering(D, StackAl, LAO, TransAl) {}
|
|
~SIFrameLowering() override = default;
|
|
|
|
void emitEntryFunctionPrologue(MachineFunction &MF,
|
|
MachineBasicBlock &MBB) const;
|
|
void emitPrologue(MachineFunction &MF,
|
|
MachineBasicBlock &MBB) const override;
|
|
void emitEpilogue(MachineFunction &MF,
|
|
MachineBasicBlock &MBB) const override;
|
|
int getFrameIndexReference(const MachineFunction &MF, int FI,
|
|
unsigned &FrameReg) const override;
|
|
|
|
void determineCalleeSaves(MachineFunction &MF, BitVector &SavedRegs,
|
|
RegScavenger *RS = nullptr) const override;
|
|
void determineCalleeSavesSGPR(MachineFunction &MF, BitVector &SavedRegs,
|
|
RegScavenger *RS = nullptr) const;
|
|
bool
|
|
assignCalleeSavedSpillSlots(MachineFunction &MF,
|
|
const TargetRegisterInfo *TRI,
|
|
std::vector<CalleeSavedInfo> &CSI) const override;
|
|
|
|
bool isSupportedStackID(TargetStackID::Value ID) const override;
|
|
|
|
void processFunctionBeforeFrameFinalized(
|
|
MachineFunction &MF,
|
|
RegScavenger *RS = nullptr) const override;
|
|
|
|
MachineBasicBlock::iterator
|
|
eliminateCallFramePseudoInstr(MachineFunction &MF,
|
|
MachineBasicBlock &MBB,
|
|
MachineBasicBlock::iterator MI) const override;
|
|
|
|
private:
|
|
void emitEntryFunctionFlatScratchInit(MachineFunction &MF,
|
|
MachineBasicBlock &MBB,
|
|
MachineBasicBlock::iterator I,
|
|
const DebugLoc &DL,
|
|
Register ScratchWaveOffsetReg) const;
|
|
|
|
Register
|
|
getEntryFunctionReservedScratchRsrcReg(MachineFunction &MF,
|
|
Register ScratchWaveOffsetReg) const;
|
|
|
|
void emitEntryFunctionScratchRsrcRegSetup(
|
|
MachineFunction &MF, MachineBasicBlock &MBB,
|
|
MachineBasicBlock::iterator I, const DebugLoc &DL,
|
|
Register PreloadedPrivateBufferReg, Register ScratchRsrcReg,
|
|
Register ScratchWaveOffsetReg) const;
|
|
|
|
public:
|
|
bool hasFP(const MachineFunction &MF) const override;
|
|
};
|
|
|
|
} // end namespace llvm
|
|
|
|
#endif // LLVM_LIB_TARGET_AMDGPU_SIFRAMELOWERING_H
|